def test_actual_results_no_numerosity_reduction():
"""Test that the actual results are the expected ones."""
bossvs = BOSSVS(
word_size=4, n_bins=3, window_size=10, window_step=10,
anova=False, drop_sum=False, norm_mean=False, norm_std=False,
strategy='quantile', alphabet=None, numerosity_reduction=False,
use_idf=True, smooth_idf=False, sublinear_tf=True
)
X_windowed = X.reshape(8, 2, 10).reshape(16, 10)
sfa = SymbolicFourierApproximation(
n_coefs=4, drop_sum=False, anova=False, norm_mean=False,
norm_std=False, n_bins=3, strategy='quantile', alphabet=None
)
y_repeated = np.repeat(y, 2)
X_sfa = sfa.fit_transform(X_windowed, y_repeated)
X_word = np.asarray([''.join(X_sfa[i])
for i in range(16)])
X_word = X_word.reshape(8, 2)
X_bow = np.asarray([' '.join(X_word[i]) for i in range(8)])
X_class = np.array([' '.join(X_bow[y == i]) for i in range(2)])
tfidf = TfidfVectorizer(
norm=None, use_idf=True, smooth_idf=False, sublinear_tf=True
)
tfidf_desired = tfidf.fit_transform(X_class).toarray()
# Vocabulary
vocabulary_desired = {value: key for key, value in
tfidf.vocabulary_.items()}
# Tf-idf
tfidf_actual = bossvs.fit(X, y).tfidf_
# Decision function
decision_function_actual = bossvs.decision_function(X)
decision_function_desired = cosine_similarity(
tfidf.transform(X_bow), tfidf_desired)
# Predictions
y_pred_actual = bossvs.predict(X)
y_pred_desired = decision_function_desired.argmax(axis=1)
# Testing
assert bossvs.vocabulary_ == vocabulary_desired
np.testing.assert_allclose(tfidf_actual, tfidf_desired, atol=1e-5, rtol=0)
np.testing.assert_allclose(
decision_function_actual, decision_function_desired, atol=1e-5, rtol=0)
np.testing.assert_allclose(
y_pred_actual, y_pred_desired, atol=1e-5, rtol=0)
drop_sum=norm_mean, window_size=window_size)
for (word_size, norm_mean, window_size) in zip(
word_size, norm_mean, window_size)]
voting = VotingClassifier([("bossvs_" + str(i), bossvs)
for i, bossvs in enumerate(bossvs)])
accuracy_BOSSVS = voting.fit(X_train, y_train).score(X_test, y_test)
print('Accuracy BOSSVS: ', accuracy_BOSSVS )
print("Error rate SAX {0:.4f}".format(1-accuracy_BOSSVS))
error_BOSSVS_list.append(1-accuracy_BOSSVS)
else:
if dataset_list == ["Adiac"]:
clf_bossvs = BOSSVS(word_size=12, n_bins=4, norm_mean=True,drop_sum=True, window_size=80)
accuracy_BOSSVS = clf_bossvs.fit(X_train, y_train).score(X_test, y_test)
print('Accuracy BOSSVS: ', accuracy_BOSSVS )
print("Error rate SAX {0:.4f}".format(1-accuracy_BOSSVS))
error_BOSSVS_list.append(1-accuracy_BOSSVS)
else:
clf_bossvs = BOSSVS(word_size=5, n_bins=4, norm_mean=False,drop_sum=False, window_size=40)
accuracy_BOSSVS = clf_bossvs.fit(X_train, y_train).score(X_test, y_test)
print('Accuracy BOSSVS: ', accuracy_BOSSVS )
print("Error rate SAX {0:.4f}".format(1-accuracy_BOSSVS))
error_BOSSVS_list.append(1-accuracy_BOSSVS)
print()
the label of the tfidf vector giving the highest cosine similarity with
the tf vector of the unlabeled time series. BOSSVS algorithm is
implemented as :class:`pyts.classification.BOSSVS`.
"""
import numpy as np
import matplotlib.pyplot as plt
from pyts.classification import BOSSVS
from pyts.datasets import load_gunpoint
# Toy dataset
X_train, X_test, y_train, y_test = load_gunpoint(return_X_y=True)
# BOSSVS transformation
bossvs = BOSSVS(word_size=2, n_bins=3, window_size=10)
bossvs.fit(X_train, y_train)
tfidf = bossvs.tfidf_
vocabulary_length = len(bossvs.vocabulary_)
X_new = bossvs.decision_function(X_test)
# Visualize the transformation
plt.figure(figsize=(14, 5))
width = 0.4
plt.subplot(121)
plt.bar(np.arange(vocabulary_length) - width / 2,
tfidf[0],
width=width,
label='Class 1')
plt.bar(np.arange(vocabulary_length) + width / 2,
tfidf[1],
def test_parameter_check(params, error, err_msg):
"""Test parameter validation."""
clf = BOSSVS(**params)
with pytest.raises(error, match=re.escape(err_msg)):
clf.fit(X, y)
import matplotlib.pyplot as plt
from pyts.classification import BOSSVS
# Parameters
n_samples, n_timestamps = 100, 144
n_classes = 2
# Toy dataset
rng = np.random.RandomState(41)
X = rng.randn(n_samples, n_timestamps)
y = rng.randint(n_classes, size=n_samples)
X[y == 0] = np.cumsum(X[y == 0], axis=1)
# BOSSVS transformation
bossvs = BOSSVS(word_size=2, n_bins=3, window_size=10)
bossvs.fit(X, y)
tfidf = bossvs.tfidf_
vocabulary_length = len(bossvs.vocabulary_)
X_new = bossvs.decision_function(X)
# Visualize the transformation
plt.figure(figsize=(16, 5))
width = 0.4
plt.subplot(121)
plt.bar(np.arange(vocabulary_length) - width / 2, tfidf[0],
width=width, label='Class 0')
plt.bar(np.arange(vocabulary_length) + width / 2, tfidf[1],
width=width, label='Class 1')
plt.xticks(np.arange(vocabulary_length),
np.vectorize(bossvs.vocabulary_.get)(np.arange(vocabulary_length)),